© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 15136
    Prev
    Next
    INDEX
    Explanations

    disclaimers and legal language related to liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hod
    -0.07
    PERT
    -0.07
    hw
    -0.07
    CardContent
    -0.07
    lw
    -0.06
    веÑī
    -0.06
    æŃ
    -0.06
    è¡Ĩ
    -0.06
    γή
    -0.06
    ANNEL
    -0.06
    POSITIVE LOGITS
     privacy
    0.07
    privacy
    0.07
     Privacy
    0.06
     Datensch
    0.06
    ickle
    0.06
    ëĿ¼ëıĦ
    0.06
    -fw
    0.06
     invisible
    0.06
    llum
    0.06
     Extended
    0.06
    Activations Density 0.000%

    No Known Activations